Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!utgpu!water!watnot!watmath!clyde!rutgers!mit-eddie!uw-beaver!ssc-vax!bcsaic!michaelm
From: michaelm@bcsaic.UUCP
Newsgroups: comp.ai
Subject: Re: dear abby....
Message-ID: <515@bcsaic.UUCP>
Date: Fri, 6-Mar-87 14:18:37 EST
Article-I.D.: bcsaic.515
Posted: Fri Mar  6 14:18:37 1987
Date-Received: Thu, 12-Mar-87 21:46:20 EST
References: <178@arcsun.UUCP> <1147@sfsup.UUCP>
Reply-To: michaelm@bcsaic.UUCP (Michael Maxwell)
Organization: Boeing Computer Services AI Center, Seattle
Lines: 42

In article <1147@sfsup.UUCP> saal@/guest5/saalUUCP (45444-AUG871-S.Saal) writes:
>In article <178@arcsun.UUCP> roy@arcsun.UUCP (Roy Masrani) writes:
>>Dear Abby.  My friends are shunning me because i think that to call
>>a program an "expert system" it must be able to explain its decisions.
>>"The system must be able to show its line of reasoning", I cry.  They
>>say "Forget it, Roy... an expert system need only make decisions that
>>equal human experts...
>
>...Once it is "in production" (the field) it may not
>be as important to give an explanation every time.  This is
>particularly the case when the expert system is used to help do
>some of the more mundane tasks on a very frequent basis.  There
>are 2 reasons for this. (1) the user may be able to agree
>intuitively after deriving the answer -  the machine has just
>helped speed the process. OR (2) If a production ES has been
>converted to a compiled language,  the code to express the
>rationale may be removed to speed up run time.

I'm not an ES expert, but when I talk to a human expert in a field, I commonly
ask "why?" or "what alternatives are there?" (which is the same thing for the
user, I think, although perhaps not for the expert).  This is even true in
"mundane" or frequently performed tasks.

An example is when I went to the AAA to ask what the best route was to drive
from Seattle to Miami in early spring.  Since I'm going to an expert for the
solution, there's a reason, and almost by definition it's not routine. 
I may have asked them how to drive from A to B many times, but in this case I
asked why they routed me the way they did, because I'm unsure of
the weather conditions over passes in Montana and Colorado.

If the ES is to not just "make decisions that equal human experts" but
replace and/or augment a human, I would want to be able to ask it the same
questions.  Hence I think that while point (2)--by deleting explanation
code we can speed up the run time system--may be true, it is beside the point
(pun).  If anything, it is an argument for faster hardware.

Or maybe I'm just suspicious...
-- 
Mike Maxwell
Boeing Advanced Technology Center
	arpa: michaelm@boeing.com
	uucp: uw-beaver!uw-june!bcsaic!michaelm